DeepAI AI Chat
Log In Sign Up

StyleBabel: Artistic Style Tagging and Captioning

03/10/2022
by   Dan Ruta, et al.
8

We present StyleBabel, a unique open access dataset of natural language captions and free-form tags describing the artistic style of over 135K digital artworks, collected via a novel participatory method from experts studying at specialist art and design schools. StyleBabel was collected via an iterative method, inspired by `Grounded Theory': a qualitative approach that enables annotation while co-evolving a shared language for fine-grained artistic style attribute description. We demonstrate several downstream tasks for StyleBabel, adapting the recent ALADIN architecture for fine-grained style similarity, to train cross-modal embeddings for: 1) free-form tag generation; 2) natural language description of artistic style; 3) fine-grained text search of style. To do so, we extend ALADIN with recent advances in Visual Transformer (ViT) and cross-modal representation learning, achieving a state of the art accuracy in fine-grained style retrieval.

READ FULL TEXT

page 8

page 11

page 14

03/17/2021

ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similarity

We present ALADIN (All Layer AdaIN); a novel architecture for searching ...
04/13/2018

Text-to-Clip Video Retrieval with Early Fusion and Re-Captioning

We propose a novel method capable of retrieving clips from untrimmed vid...
07/29/2022

ALADIN: Distilling Fine-grained Alignment Scores for Efficient Image-Text Matching and Retrieval

Image-text matching is gaining a leading role among tasks involving the ...
09/28/2022

TokenFlow: Rethinking Fine-grained Cross-modal Alignment in Vision-Language Retrieval

Most existing methods in vision-language retrieval match two modalities ...
10/12/2021

Fine-grained style control in Transformer-based Text-to-speech Synthesis

In this paper, we present a novel architecture to realize fine-grained s...
06/13/2018

Cross-modal Hallucination for Few-shot Fine-grained Recognition

State-of-the-art deep learning algorithms generally require large amount...
04/23/2018

Beyond Narrative Description: Generating Poetry from Images by Multi-Adversarial Training

Automatic generation of natural language from images has attracted exten...